Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 77388
    Prev
    Next
    INDEX
    Explanations

    Mixed languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ————————————————
    -0.08
     gostei
    -0.08
     electrónico
    -0.08
     Cherokee
    -0.07
     nasty
    -0.07
    issed
    -0.07
    isses
    -0.07
     veril
    -0.07
    @Get
    -0.07
    [obj
    -0.07
    POSITIVE LOGITS
     rollen
    0.08
     rolls
    0.08
    unden
    0.08
    λί
    0.07
     argumentative
    0.07
    units
    0.07
    _roll
    0.07
    inten
    0.07
    ueble
    0.07
    orang
    0.07
    Activations Density 0.000%

    No Known Activations